Triple

T5188314
Position Surface form Disambiguated ID Type / Status
Subject Blue Thunder E117085 entity
Predicate editedBy P1954 FINISHED
Object Edward M. Abroms E526290 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Edward M. Abroms | Statement: [Blue Thunder, editedBy, Edward M. Abroms]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edward M. Abroms
Context triple: [Blue Thunder, editedBy, Edward M. Abroms]
  • A. Edward M. Abroms chosen
    Edward M. Abroms was an American film and television editor and director, noted for his work on major projects in the 1960s and 1970s and for winning both an Academy Award and an Emmy for editing.
  • B. Gerald W. Abrams
    Gerald W. Abrams is an American television producer known for his work on TV movies and series and as the father of filmmaker J. J. Abrams.
  • C. Edward A. Garmatz
    Edward A. Garmatz was a long-serving U.S. Congressman from Maryland who represented Baltimore in the House of Representatives in the mid-20th century.
  • D. Maurice L. Zigmond
    Maurice L. Zigmond was an American anthropologist and linguist known for his extensive documentation and analysis of Native Californian languages and cultures, including the Kawaiisu.
  • E. Edward S. Feldman
    Edward S. Feldman is an American film producer known for overseeing a range of notable movies across several decades, including acclaimed dramas and thrillers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69bd44620ff48190bcac01782107a397 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd79c56280819085926316f7b520bc completed March 20, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11c83f8bc8190bdf139c9da2dd66b completed March 23, 2026, 10:57 a.m.
Created at: March 20, 2026, 1:46 p.m.